AGENT SKILL

fulcra-agent-coordination

Coordination layer over fulcra-workspaces: presence and liveness, durable roles with leases, resumable continuity, a review handshake, directed work with acks, and fleet health — folded deterministically by a vendored, stdlib-only engine.

License 许可
MIT
最近更新
2026-10-23
Stars
★ 3
Forks
6

01 前言 Front Matter

name
fulcra-agent-coordination
license
MIT
homepage
https://github.com/fulcradynamics/community-skills
metadata
{ "openclaw": { "emoji": "🧭" } }
description
Coordination layer over fulcra-workspaces: presence and liveness, durable roles with leases, resumable continuity, a review handshake, directed work with acks, and fleet health — folded deterministically by a vendored, stdlib-only engine.
user-invocable
true

02 资源文件 59

03 SKILL.md 正文

Fulcra Agent Coordination

The coordination layer over the fulcra-workspaces skill (fulcradynamics/agent-skills). Teams gives a group of agents shared memory, inboxes, and versioned files. This skill adds what teams deliberately leaves out: presence (who is alive right now), roles (durable functions held by lease, not by session), continuity (structured snapshots and a deterministic resume brief), review (an N-reviewer verdict tally), directives (directed work with priorities and acks), and health (is anything actually running, and which host went dark).

The through-line: anything two agents must agree on is a fold over derived state, computed by the engine, rather than a prose instruction telling each agent to compare timestamps and reach its own conclusion. Two agents folding the same state get the same answer; two agents interpreting it do not.

The engine is an adapted vendored subset, not an automatically synchronized dependency. See ALIGNMENT.md and upstream-selection.json for the historical provenance limitation, exact current comparison commit, included modules, exclusions, and read-only drift check.

Invoking the engine

The engine ships with this skill at scripts/coord-engine — stdlib-only Python 3, no install step and no dependencies to resolve. Every command in this skill is spelled <skill-dir>/scripts/coord-engine …, where <skill-dir> is this skill's directory.

<skill-dir>/scripts/coord-engine --help     # the verb list
<skill-dir>/scripts/coord-engine doctor <team>   # preflight: tooling + store reachability

Writes go to the Fulcra File Store, so the storage CLI must be authenticated. Don't run a bare fulcra-api auth login — it launches a browser and polls for up to two minutes, which reads as a stuck command. Use the non-interactive two-step instead:

fulcra-api auth login --get-auth-url                 # prints a URL + device code, then exits
# hand the URL to your user; they authorize in a browser
fulcra-api auth login --device-code <DEVICE_CODE>    # completes auth and persists the token

Then re-run doctor to confirm; it checks exactly that.

One-shot inbox reads, not a resident listener

The engine deliberately has no resident listen command. Read an agent's work once with:

<skill-dir>/scripts/coord-engine inbox <team> --agent <you> --json

If the team needs recurring unattended work, let the agent harness, cron, or heartbeat scheduler wake the agent and run one bounded inbox read per wake. Do not build a polling loop around the engine. This keeps liveness and retry policy visible to the operator, prevents duplicate hidden daemons, and makes a slow or failed store read affect one wake instead of wedging a long-running process.

These are layers, not alternatives

Teams is the base. The six below are optional layers on top of it, not competing options to choose between — they share one engine and one team namespace, and they compose: broadcasts use the presence roster; role vacancy escalates through directives; handoff writes a continuity checkpoint; health reports on whatever reconcile schedule you run. Adopt the whole thing and use what your situation calls for.

Each layer degrades cleanly when a layer it likes is absent, and says so where it matters: briefing on a cold team prints empty sections rather than failing; a broadcast without presence still hides acked items per-agent, it just can't tell you when everyone has seen it. Nothing here requires you to decide up front which layers you are "installing".

There is no need to read all six references. Run the probe that matches your question and read the reference it points at.

Router

<you> is your agent id (see presence on picking one). Probes are read-only.

Probe Command Passes when If it fails, read
Is the engine reaching the store? <skill-dir>/scripts/coord-engine doctor <team> exit 0 health.md
Cold start — what is this team's state? <skill-dir>/scripts/coord-engine briefing <team> --agent <you> exit 0; prints the presence/board/inbox/needs-me sections (empty sections are a pass) continuity.md
Who is alive right now? <skill-dir>/scripts/coord-engine presence show <team> --json your row shows "liveness": "live" presence.md
Does anyone hold this role? <skill-dir>/scripts/coord-engine roles status <team> <role> --json exit 0 and "status": "HELD"; exit 1 means the transport is degraded and the role's state is unknown — retry rather than treating it as VACANT roles.md
Can I resume what I left? <skill-dir>/scripts/coord-engine continuity resume <team> <you> prints an objective and next actions continuity.md
Do I have directed work waiting? <skill-dir>/scripts/coord-engine inbox <team> --agent <you> --json exit 0 and a JSON array with no leading inbox-degraded row; each invocation is one bounded read directives.md
Is this artifact cleared to land? <skill-dir>/scripts/coord-engine review status <team> <slug> --json "state": "APPROVED" with empty pending_required; exit 1 means the tally is unknown — retry rather than treating it as unapproved review.md
Is anything actually reconciling this team? <skill-dir>/scripts/coord-engine health <team> --json exit 0 and "healthy": true health.md

What's yours to decide

Where a decision belongs to you rather than to the skill, the references mark it User's call: and stop there. The engine computes state; it does not hold opinions about how you run a team. The recurring ones:

  • Heartbeat cadence — how often agents beat presence and how often reconcile runs. Everything downstream (roster freshness, inbox lag, health's STALE flag) is bounded by what you pick.
  • Which roles exist, their policy (shared/exclusive), sla_hours, and maintainer. There is no built-in vocabulary and no default org chart.
  • Whether unattended operator wakes run at all — draining inboxes, storing digests, sweeping vacancies — or whether a human drives those actions.
  • What review gates in your process, and whether required reviewers are roles or named agents.
  • Snapshot cadence, and whether sessions end with continuity park or a bare snapshot.

References

  • presence.md — heartbeat shard, liveness folds, picking an agent id by role.
  • roles.md — role docs, leases, HELD/VACANT/CONTESTED/DORMANT, vacancy escalation.
  • continuity.md — snapshot schema, resume brief, role checkpoints, park, briefing.
  • review.md — request, verdicts, the APPROVED/CHANGES/PENDING tally.
  • directives.md — tell/broadcast/remind/later/handoff/inbox/respond, acks.
  • health.md — doctor, fleet health fold, operator digest, escalation sweep.

04 同仓库更多 Skills

fulcradynamics
fulcradynamics/community-skills

use-agents-for-pre-networking-at-events

Pre-network at a conference or event run on Agent Mixer: put your person on Fulcra, learn what they want from the event, share their attendee card with other attendees, pick who they should meet, negotiate with other attendees' agents, and schedule meetings they approve. Use when the user shares an Agent Mixer event link (agentmixer.my.fulcra.ai/e/...), or says get me ready for this event, who should I meet at <event>, set up meetings at <event>, or check my Agent Mixer meetups.

★ 3
fulcradynamics
fulcradynamics/community-skills

trade-agent-hacks-by-invite

Start or join an invite-only network on Fulcra where people's agents trade hacks (tips, tricks, prompts and skills that make an agent more useful). Use when the user wants to set up their own hack-trading network, has an invite to one (for example The Secret Agent Network), or wants to submit a hack, check clearance, get new hacks, ask or answer a question about a hack, or send invites.

★ 3
fulcradynamics
fulcradynamics/community-skills

track-my-dealflow

Use when a content creator asks about their brand deals, contracts, what's due, who owes them, or anything in Track My Dealflow (track-my-dealflow.my.fulcra.ai).

★ 3
fulcradynamics
fulcradynamics/community-skills

fulcra-vault

Manage a durable, Obsidian-like shared markdown knowledge vault using Open Knowledge Format (OKF) stored in Fulcra, enabling persistent shared memory across all agents.

★ 3
fulcradynamics
fulcradynamics/community-skills

fulcra-sister-cities

Run or facilitate Sister Cities, an asynchronous city-trade social game for 3–10 players. Cities are light social-game flavour; players trade everyday imports such as candy, soft drinks, books, games, plants, and small comforts, with automatic redacted round editions.

★ 3
fulcradynamics
fulcradynamics/community-skills

fulcra-project-dashboard

Builds a management dashboard for an agent-teams workspace, showing progress, logs, a generated summary, timeline/milestone charts, and a word map of agent activities.

★ 3